ClawHub
Back to skill

Security audit

Pressmark Real Estate & Property Management

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses its external document service and requests information consistent with preparing real-estate documents.

Use this skill only if Pressmark is suitable for your document data. Review its privacy and retention terms, and omit unnecessary personal or banking details.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The workflow sends sensitive real-estate and financial details to a third-party document service without a privacy warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The workflow collects identifying property and party information plus financial terms, including escrow banking details, for document generation through an external MCP service without explicitly disclosing the sensitive-data transfer or obtaining informed approval. Although remote compilation is a legitimate part of this skill, real-estate documents can expose tenant, owner, and banking information to unauthorized retention, access, or reuse if the provider's handling is unsuitable. The service is openly identified and there is no evidence of malicious exfiltration, but the instruction not to request credentials does not adequately protect other sensitive financial and personal data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.